Claude Skills by paulasilvatech

Create an integration testing plan for one .NET project during Oracle-to-PostgreSQL migration. Use when planning coverage for repositories, DAOs, stored procedure callers, CRUD service layers, Oracle-specific behavior, seed data, or migration validation cases before writing integration tests.

Review Oracle-to-PostgreSQL migration plans or completed artifacts for behavioral risks: empty strings, exceptions, refcursors, type coercion, sorting and collations, UNION ALL planner changes, materialized-view refresh, timestamps, sequences, ROWNUM, NVL/DECODE, and concurrent transactions. Use when planning or validating database migrations and integration tests.

Scaffold a compilable xUnit integration test project for a .NET Oracle application before Oracle-to-PostgreSQL migration testing. Use when Phase 3 requires an Oracle baseline test project, transaction rollback infrastructure, seed data management, or an empty integration-test harness before writing tests.

Find sponsorable direct and transitive dependencies for a GitHub repository using deps.dev, GitHub funding files, npm funding metadata, verified funding links, and OSSF Scorecard health data. Use this skill when the user invokes /sponsor owner/repo, asks which dependencies can be sponsored, or wants GitHub Sponsors, Open Collective, Ko-fi, Patreon, or Tidelift funding coverage.

Design, implement, review, and package Power Apps Component Framework code components for model-driven apps, canvas apps, and Power Pages. Use when the user asks about PCF manifests, lifecycle APIs, dataset or field controls, React platform libraries, PAC CLI tooling, ALM, performance, accessibility, security, testing, or deployment.

Debug LLM applications using the Phoenix CLI. Fetch traces, analyze errors, structure trace review with open coding and axial coding, inspect datasets, review experiments, query annotation configs, and use the GraphQL API. Use when the user is analyzing traces or spans, investigating LLM/agent failures, deciding what to do after instrumenting an app, building failure taxonomies, choosing what evals to write, or asking "what's going wrong", "what kinds of mistakes", or "where do I focus" — eve...

Build, run, validate, and operationalize Phoenix evaluators for AI and LLM applications in Python or TypeScript, including code evaluators, LLM judges, RAG evals, experiments, datasets, tracing, sampling, error analysis, and production guardrails. Use when the user asks for Phoenix evals, evaluator design, judge validation, experiments, or AI quality monitoring.

Instrument Python and TypeScript LLM applications with Phoenix AI observability using OpenInference semantic conventions, arize-phoenix-otel, @arizeai/phoenix-otel, spans, sessions, metadata, annotations, and production masking. Use when setting up Phoenix tracing, creating custom spans, adding OpenInference attributes, or deploying tracing to production.

Generate a complete PHP Model Context Protocol server project with tools, resources, prompts, tests, and Claude Desktop configuration using the official PHP SDK. Use this skill when the user asks for a PHP MCP server, PHP SDK MCP project, stdio or HTTP MCP transport, tool/resource/prompt scaffolding, or production-ready MCP server requirements.

Triage public Shopify App Store reviews into a P0-P3 product or support brief while preserving source links, first-pass labels, and human-check status. Use when asked to "triage app store reviews", "cluster 1-star reviews", "prioritize Shopify merchant feedback", "write a low-star review brief", or "decide what to fix first from public reviews".

Scaffold a Power Apps Code Apps preview project with Vite, React, TypeScript, PAC CLI, Power Apps SDK, PowerProvider, connector services, Fluent UI, package scripts, README, and deployment guidance. Use when asked to create, initialize, or configure a code-first Power Apps Code App project, add supported connectors, or prepare pac code push deployment.

Analyze and optimize Power BI DAX formulas for performance, readability, maintainability, variables, context transitions, filter efficiency, safe division, and best-practice function choice. Use when the user asks for a Power BI DAX formula optimizer, slow measure review, DAX refactor, or optimized measure with explanation.

Review Power BI data model architecture, relationships, storage modes, performance, security, governance, and maintainability. Use this skill when asked for a Power BI model design review, star schema assessment, relationship design evaluation, pre-production model review, modernization assessment, or optimization roadmap.

Diagnose and resolve Power BI performance issues across semantic models, reports, DAX, refresh, DirectQuery, gateways, and Fabric or Premium capacity. Use this skill when asked to troubleshoot slow Power BI reports, page loading, visual interactions, query execution, model refresh, capacity pressure, or gateway bottlenecks.

Design effective Power BI report layouts, chart selections, interactions, accessibility, mobile views, and implementation guidance. Use when asked for Power BI visualization design, dashboard layout, chart choice, KPI report structure, slicer/navigation design, accessibility review, mobile report design, or report UX consultation.

Transform business requirements, use case descriptions, and meeting transcripts into Power Platform solution architecture with component selection, process narrative, follow-up questions, and optional Mermaid.js diagrams. Use when asked to design a Power Apps, Power Automate, Dataverse, Power BI, Power Pages, Microsoft Copilot Studio, connector, gateway, or AI Builder architecture from discovery material.

Generate a complete MCP server and Power Platform custom connector optimized for Microsoft Copilot Studio, including streamable HTTP, JSON-RPC 2.0, schema constraints, apiDefinition.swagger.json, apiProperties.json, script.csx, tools, resources-as-tool-outputs, deployment, and validation. Use when asked for a Power Platform MCP connector generator or Copilot Studio MCP integration.

Generate and validate Power Platform custom connectors that expose Model Context Protocol servers to Microsoft Microsoft Copilot Studio, including Swagger, apiProperties.json, script.csx, JSON-RPC 2.0 handling, schema compliance, OAuth hardening, certification preparation, and troubleshooting. Use when asked for MCP capabilities in Microsoft Copilot Studio, a custom connector for MCP tools/resources, or paconn/pac connector validation.

Generate draw.io diagrams as native .drawio files and export them to PNG, SVG, or PDF with embedded XML. Use when the user asks for draw.io diagrams, diagrams.net XML, mxGraphModel, editable diagram source, or exporting .drawio files for documents.

Convert Markdown files to professionally formatted Word .docx documents with title page metadata, table of contents, styled tables, code blocks, links, and embedded PNG images using pure JavaScript. Use when the user asks to convert Markdown to Word, produce a .docx from .md, embed PNG diagrams, or run the bundled Node converter without Pandoc or LibreOffice.

Create a high-level epic architecture specification from an Epic PRD, including system diagrams, technical enablers, stack choices, technical value, and t-shirt sizing. Use when asked to write an epic architecture spec, turn a PRD into architecture, or produce docs/ways-of-work arch.md.

Create an Epic Product Requirements Document (PRD) from a high-level epic idea, including goal, personas, journeys, business requirements, success metrics, scope boundaries, and business value. Use when asked to write an epic PRD or docs/ways-of-work epic.md.

Create detailed feature implementation plans from a Feature PRD for an Epoch-style monorepo, including architecture, database schema, API design, frontend structure, security, performance, and deployment considerations. Use this skill when the user asks for a feature implementation plan, feature breakdown, PRD-to-plan conversion, or implementation-plan.md.

Create a detailed feature Product Requirements Document from an epic and feature idea, including goal, personas, user stories, functional and non-functional requirements, acceptance criteria, and out-of-scope boundaries. Use when asked to write a feature PRD or docs/ways-of-work feature prd.md.

Create or update GitHub issues from implementation-plan phases using feature_request.yml or chore_request.yml templates when available. Use when the user asks to turn an implementation plan into GitHub issues, file one issue per phase, or deduplicate planned feature/chore work against existing issues.

Create deterministic implementation plan files for features, refactors, package upgrades, design, architecture, infrastructure, data, or process work. Use when the user asks for an implementation plan, phased execution plan, AI-executable plan, /plan artifact, or machine-readable roadmap for autonomous agents or humans.

Create time-boxed technical spike documents that answer critical implementation questions before development proceeds. Use this skill when the user asks to create a technical spike, research an API or architecture decision, document a proof of concept, evaluate performance or security options, or unblock development with an evidence-based recommendation.

Update an existing implementation plan or create a deterministic machine-readable plan for new requirements, features, refactoring, package upgrades, design, architecture, infrastructure, data, or process changes. Use when asked to update an implementation plan, revise a plan file, add requirements, or produce an AI-executable plan under /plan/.

Generate a complete Python Model Context Protocol server project using uv, mcp[cli], FastMCP, typed tools, optional resources and prompts, stdio or streamable-http transport, error handling, and testing instructions. Use when the user asks to generate a Python MCP server, create an MCP tool server, scaffold FastMCP, or build a streamable HTTP MCP service.

Select and use official Qdrant client SDKs, REST API, gRPC API, and curated snippet search. Use this skill when the user asks for Qdrant API reference, client installation commands, SDK language choice, upload point examples, FastEmbed setup, or REST versus gRPC guidance.

Select the right Qdrant deployment model across local mode, Docker self-hosting, Qdrant Cloud, Hybrid Cloud, distributed deployment, and Qdrant EDGE. Use when someone asks how to deploy Qdrant, Docker vs Cloud, embedded Qdrant, local mode, self-hosted vs cloud, lowest latency, data residency, production readiness, or which deployment option fits a new vector search project.

Plan zero-downtime embedding model migrations in Qdrant with aliases, re-embedding, side-by-side collections, hybrid dense/sparse search, and bulk upload tuning. Use when switching embedding models, changing vector dimensions or providers, upgrading to hybrid search, re-embedding data, or A/B testing models.

Guide Qdrant monitoring, observability, health checks, Prometheus, Grafana, alerting, log centralization, and metric-based production debugging. Use when users ask how to monitor Qdrant, what metrics to track, whether Qdrant is healthy, why optimizers are stuck, why memory is growing, why requests are slow, or how to set up Prometheus or Grafana.

Diagnoses Qdrant production issues using metrics and observability tools. Use when someone reports 'optimizer stuck', 'indexing too slow', 'memory too high', 'OOM crash', 'queries are slow', 'latency spike', or 'search was fast now it's slow'. Also use when performance degrades without obvious config changes.

Guides Qdrant monitoring setup including Prometheus scraping, health probes, Hybrid Cloud metrics, alerting, and log centralization. Use when someone asks 'how to set up monitoring', 'Prometheus config', 'Grafana dashboard', 'health check endpoints', 'how to scrape Hybrid Cloud', 'what alerts to set', 'how to centralize logs', or 'audit logging'.

Diagnose and optimize Qdrant performance across search speed, indexing throughput, memory usage, query shape, HNSW and payload indexes, quantization, storage, and hardware trade-offs. Use when asked to improve Qdrant latency, throughput, indexing speed, RAM usage, or vector search efficiency.

Diagnoses and fixes slow Qdrant indexing and data ingestion. Use when someone reports 'uploads are slow', 'indexing takes forever', 'optimizer is stuck', 'HNSW build time too long', or 'data uploaded but search is bad'. Also use when optimizer status shows errors, segments won't merge, or indexing threshold questions arise.

Diagnoses and reduces Qdrant memory usage. Use when someone reports 'memory too high', 'RAM keeps growing', 'node crashed', 'out of memory', 'memory leak', or asks 'why is memory usage so high?', 'how to reduce RAM?'. Also use when memory doesn't match calculations, quantization didn't help, or nodes crash during recovery.

Diagnoses and fixes slow Qdrant search. Use when someone reports 'search is slow', 'high latency', 'queries take too long', 'low QPS', 'throughput too low', 'filtered search is slow', or 'search was fast but now it's slow'. Also use when search performance degrades after config changes or data growth.

Guide Qdrant scaling decisions for data volume, query throughput, query latency, query volume, tenant growth, sharding, and capacity planning. Use when someone asks how many nodes are needed, whether to scale vertically or horizontally, why a cluster is slow, how to shard, or how to add capacity.

Guides Qdrant query latency optimization. Use when someone asks 'search is slow', 'how to reduce latency', 'p99 is too high', 'tail latency', 'single query too slow', 'how to make search faster', or 'latency spikes'.

Diagnoses and guides Qdrant horizontal scaling decisions. Use when someone asks 'vertical or horizontal?', 'how many nodes?', 'how many shards?', 'how to add nodes', 'resharding', 'data doesn't fit', or 'need more capacity'. Also use when data growth outpaces current deployment.

Guides sliding time window scaling in Qdrant. Use when someone asks 'only recent data matters', 'how to expire old vectors', 'time-based data rotation', 'delete old data efficiently', 'social media feed search', 'news search', 'log search with retention', or 'how to keep only last N months of data'.

Guides Qdrant multi-tenant scaling. Use when someone asks 'how to scale tenants', 'one collection per tenant?', 'tenant isolation', 'dedicated shards', or reports tenant performance issues. Also use when multi-tenant workloads outgrow shared infrastructure.

Guides Qdrant vertical scaling decisions. Use when someone asks 'how to scale up a node', 'need more RAM', 'upgrade node size', 'vertical scaling', 'resize cluster', 'scale up vs scale out', or when memory/CPU is insufficient on current nodes. Also use when someone wants to avoid the complexity of horizontal scaling.

Guides Qdrant query throughput (QPS) scaling. Use when someone asks 'how to increase QPS', 'need more throughput', 'queries per second too low', 'batch search', 'read replicas', or 'how to handle more concurrent queries'.

Diagnose and improve Qdrant search relevance by separating embedding, payload, index, and query-strategy causes. Use when users report bad search results, wrong results, low precision, low recall, irrelevant matches, missing expected results, quantization regressions, model changes, data growth, or ask whether to use hybrid search, reranking, relevance feedback, or a different embedding model.

Diagnoses Qdrant search quality issues. Use when someone reports 'results are bad', 'wrong results', 'not relevant results', 'missing matches', 'recall is low', 'approximate search worse than exact', 'which embedding model', or 'quality dropped after quantization'. Also use when search quality degrades without obvious changes.

Guides Qdrant search strategy selection. Use when someone asks 'should I use hybrid search?', 'BM25 or sparse vectors?', 'how to rerank?', 'results are not relevant', 'I don't get needed results from my dataset but they're there', 'retrieval quality is not good enough', 'results too similar', 'need diversity', 'MMR', 'relevance feedback', 'recommendation API', 'discovery API', 'ColBERT reranking', or 'missing keyword matches'

Plan Qdrant server, SDK, storage, cluster, rolling, and Qdrant Cloud upgrades without interrupting availability or risking data integrity. Use this skill when the user asks how to upgrade Qdrant, move between minor versions, match SDK and server versions, perform a rolling upgrade, or use qcloud for Qdrant Cloud upgrades.